NSFW Wan 14b needs about 11.3 GB of memory at Q4_K (a 9.7 GB file) with an 8K context window, so it fits on a 12 GB GPU.
NSFW Wan 14b – a 14 billion‑parameter text‑to‑video model for adult content.
NSFW Wan 14b is a 14 billion‑parameter text‑to‑video transformer fine‑tuned for NSFW content. It generates short video clips from text prompts with coherent motion and high fidelity. The model is released under the creativeml‑openrail‑m license.
Good at
- High‑fidelity NSFW video generation
- Coherent motion in 480p clips
- Text‑driven content creation
Limits
- Requires 11.3 GB VRAM at 8k context (Q4_K)
- No vision or multimodal support
- License restricts commercial use
Best for
- Research on adult content generation
- Creative video prototyping
- Educational demonstrations of text‑to‑video pipelines
Who it’s for. Researchers and developers needing a large‑scale, open‑source text‑to‑video model specialized in NSFW content. The model is suitable for academic studies and non‑commercial creative projects.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 9.7 GB | 11.3 GB | Too big | Get file → |
For 8 GB VRAM, the Q4_K quant is the only available option and requires approximately 11.3 GB VRAM at 8k context. If more memory is available, the same quant can be used; no other quants are provided.
What GPU do you need for NSFW Wan 14b?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_K (9.7 GB file, about 11.3 GB in use).
Which NSFW Wan 14b quant should you choose?
Q4_K (9.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NSFW Wan 14b
How much VRAM does NSFW Wan 14b need?
About 11.3 GB at Q4_K with an 8K context window. That is the 9.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run NSFW Wan 14b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NSFW Wan 14b GGUF?
It depends on the quant: Q4_K is 9.7 GB.
Where can I download NSFW Wan 14b GGUF?
The files are on Hugging Face in the NSFW-API/NSFW_Wan_14b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does NSFW Wan 14b use?
Hugging Face lists the license as creativeml-openrail-m. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Does the model support image or text‑to‑image tasks?
No, it is a text‑to‑video model only and does not support image generation.
Is the model suitable for commercial use?
The creativeml‑openrail‑m license restricts commercial use; it is intended for research and non‑commercial projects.